On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines

ArXi:2508.14482v3 Announce Type: replace The explainability of deep learning models remains a significant challenge, particularly in the medical domain where interpretable outputs are essential for clinical trust and transparency. Path attribution methods such as Integrated Gradients rely on a baseline that represents the absence of informative features, a notion commonly referred to as missingness. Standard baselines, such as all-zero inputs, are often semantically meaningless in medical contexts, where intensity values carry clinical significance.